Welcome to the World of Binomial Expectations!

In this chapter of your OCR A Level Mathematics B (MEI) course, we are moving from calculating the probability of a specific event to looking at the "big picture." We will learn how to calculate the mean (the average outcome) and expected frequencies (how often we expect something to happen over many trials).

Don’t worry if these terms sound a bit technical at first! Think of it like this: if you know you have a 1 in 10 chance of winning a prize, and you play 100 times, your gut feeling tells you that you should win about 10 times. That "gut feeling" is actually the mean! Let's dive into how we calculate this precisely.


1. The Mean of a Binomial Distribution

In the Binomial Distribution \( B(n, p) \), the mean represents the average number of "successes" we expect to see across \( n \) trials.

The formula is surprisingly simple:

Mean \( (\mu) = np \)

Where:
\( n \) = the number of trials (how many times you do the thing).
\( p \) = the probability of success in a single trial.

Why does this work? (An Analogy)

Imagine you are practicing basketball free throws. Your success rate (\( p \)) is 0.7 (or 70%). If you take 10 shots (\( n = 10 \)), how many do you expect to make?
You simply do \( 10 \times 0.7 = 7 \).
You expect to make 7 shots. This is the mean of your distribution!

Quick Review: The Symbolism

In your exam, you might see the mean written as \( E(X) \), which stands for the Expected Value of X. For a Binomial Distribution, \( E(X) \) and the mean \( \mu \) are exactly the same thing: \( np \).

Did you know?
The mean of a binomial distribution doesn't have to be a whole number. If you flip a coin 5 times, the mean number of heads is \( 5 \times 0.5 = 2.5 \). Even though you can't actually get 2.5 heads in a single experiment, 2.5 is the long-term average if you repeated the experiment thousands of times!

Key Takeaway: To find the average number of successes, just multiply the number of trials by the probability of success. Mean = \( np \).


2. Expected Frequencies

While the mean tells us the average number of successes in one set of \( n \) trials, expected frequencies tell us how many times we expect a *specific* result to occur if we repeat the whole experiment many times.

The Formula for Expected Frequency

If you repeat an experiment \( N \) times, the expected frequency of a specific outcome is:
Expected Frequency \( = N \times P(X = r) \)

Where:
\( N \) = the total number of times the whole experiment is repeated.
\( P(X = r) \) = the probability of getting exactly \( r \) successes in one experiment (calculated using the binomial formula or your calculator).

Step-by-Step Example

Suppose a seed has a 0.8 probability of germinating. You plant them in pots of 5 seeds each (\( n = 5 \)). You have 100 such pots (\( N = 100 \)). How many pots do you expect to have exactly 3 seeds germinate?

1. Identify the distribution: \( X \sim B(5, 0.8) \).
2. Calculate the probability for one pot: Use your calculator to find \( P(X = 3) \).
\( P(X = 3) = \binom{5}{3} \times 0.8^3 \times 0.2^2 = 0.2048 \).
3. Multiply by the number of repetitions (\( N \)):
Expected Frequency \( = 100 \times 0.2048 = 20.48 \).
Conclusion: You would expect approximately 20 or 21 pots to have exactly 3 seeds germinate.

Key Takeaway: Expected frequency is simply the Total Repetitions (\( N \)) times the Probability of the outcome. It helps us compare theoretical models to real-world data.


3. Common Mistakes to Avoid

Even the best students can trip up on these small details. Keep an eye out for these:

  • Confusing \( n \) and \( N \): In your notes and exams, \( n \) is usually the number of trials within one binomial experiment, while \( N \) is how many times you repeat that entire experiment. Always read the question carefully to see which is which!
  • Using \( q \) instead of \( p \): Remember that the mean is based on successes (\( p \)). If a question gives you the probability of failure (\( q \)), subtract it from 1 first!
  • Rounding too early: When calculating \( P(X = r) \), keep as many decimal places as possible before multiplying by \( N \). Rounding early can lead to a significant error in your final expected frequency.

4. Summary Table for Quick Revision

Use this box to check your understanding before moving on to practice questions!

1. Binomial Notation: \( X \sim B(n, p) \)
2. Probability of Success: \( p \)
3. Number of Trials: \( n \)
4. Mean / Expected Successes: \( \mu = np \)
5. Expected Frequency of \( r \) successes: \( N \times P(X = r) \)


Final Words of Encouragement

The concepts of mean and expected frequencies are the bridge between "pure math" and "real-world statistics." By mastering \( np \), you are learning how to predict the future (on average, at least!). Don't worry if the distinction between mean and expected frequency feels a bit blurry at first—with a few practice problems, the logic will click. You've got this!